@article{TACL582,
	author = {Dat Quoc Nguyen and Richard Billingsley and Lan Du and Mark
Johnson},
	title = {Improving Topic Models with Latent Feature Word Representations},
	journal = {Transactions of the Association for Computational Linguistics},
	volume = {3},
	year = {2015},
	keywords = {},
	abstract = {Probabilistic topic models are widely used to discover latent
topics in document collections, while latent feature vector representations
of words have been used to obtain high performance in many NLP tasks. In
this paper, we extend two different Dirichlet multinomial topic models by
incorporating latent feature vector representations of words trained on very
large corpora to improve the word-topic mapping learnt on a smaller corpus.
Experimental results show that by using information from the external
corpora, our new models produce significant improvements on topic coherence,
document clustering and document classification tasks, especially on
datasets with few or short documents.},
	issn = {2307-387X},
	url =
{https://tacl2013.cs.columbia.edu/ojs/index.php/tacl/article/view/582},
	pages = {299--313}
}